CN115186054A - Fault visualization analysis method and system - Google Patents
Fault visualization analysis method and system Download PDFInfo
- Publication number
- CN115186054A CN115186054A CN202210748871.6A CN202210748871A CN115186054A CN 115186054 A CN115186054 A CN 115186054A CN 202210748871 A CN202210748871 A CN 202210748871A CN 115186054 A CN115186054 A CN 115186054A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- sentence
- text
- real
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/374—Thesaurus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
- G06N5/025—Extracting rules from data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method and the system for visually analyzing the fault are particularly applied to the field of data processing and comprise the steps of collecting historical data; preprocessing the historical data to obtain a knowledge text; extracting entity, attribute and relation triples in the knowledge text; constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result; acquiring real-time monitoring data and a real-time running state of target equipment; extracting abnormal data in the real-time monitoring data according to the knowledge graph; calculating credibility scores between the abnormal data and each fault type; determining a target fault type corresponding to the abnormal data based on the credibility score; determining a fault analysis result according to a mapping relation between the real-time running state and the target fault type; rendering the fault analysis result and carrying out visual display. Therefore, the accuracy of fault analysis is improved, and operation and maintenance personnel can obtain the operation condition of the equipment in real time.
Description
Technical Field
The present application relates to the field of data processing, and in particular, to a fault visualization analysis method and system.
Background
After the off-grid island intelligent micro-grid project of the self-driving island is put into operation, a power grid company carries out the work of micro-grid remote monitoring, daily operation and maintenance, emergency guarantee, micro-grid power protection, technical personnel training and the like.
In order to ensure safe and stable operation of the microgrid device, the device fault needs to be diagnosed quickly and accurately. With the rapid development of big data technology, experts in the field successively put forward various fault analysis methods, such as gas chromatography, expert systems, vibration methods, fuzzy theory, and the like. However, these methods are mostly suitable for the situation that the equipment has a simple single fault, and because the microgrid has many power supply points, unbalanced power consumption for power generation, and is easily affected by uncertain factors such as weather, the equipment fault presents complexity and diversity, the existing analysis technology has low working efficiency, and it is difficult to timely and effectively process the sudden abnormality and fault.
Therefore, a time-efficient fault visualization analysis method is urgently needed at present, and scientific support is provided for intelligent operation and maintenance, monitoring and early warning and fault treatment of the microgrid.
Disclosure of Invention
The embodiment of the invention aims to provide a fault visual analysis method and system, which can determine a target fault type corresponding to abnormal data in real-time monitoring data of equipment by calculating a credibility score, and further visually display a fault analysis result. Therefore, the accuracy of fault analysis is improved, and operation and maintenance personnel can obtain the running condition of the equipment in real time. The specific technical scheme is as follows:
in a first aspect of the embodiments of the present invention, a fault visualization analysis method is provided, including: collecting historical data; preprocessing the historical data to obtain a knowledge text; extracting entity, attribute and relation triples in the knowledge text; constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result; acquiring real-time monitoring data and a real-time running state of target equipment; extracting abnormal data in the real-time monitoring data according to the knowledge graph; calculating the credibility scores between the abnormal data and each fault type, wherein the formula is as follows:
wherein Q is m Representing a confidence score between the anomaly data and a fault type m, H representing the anomaly data, H = { t = { (m) } 1 ,t 2 ,…,t i ,…,t n }，t i Representing the ith data in the abnormal data;
represents t i The weight of (a) is calculated,
represents t i Number of occurrences in fault type m, N m The total occurrence frequency of the fault type m in the previous year is represented, and the total fault frequency in the previous year is represented by N; determining a target fault type corresponding to the abnormal data based on the credibility score; determining a fault analysis result according to a mapping relation between the real-time running state and the target fault type; and rendering the fault analysis result and performing visual display.
Optionally, the preprocessing the historical data to obtain a knowledge text includes: rejecting non-text data in the historical data to obtain a historical text; sentence dividing processing is carried out on the historical text, and a sentence dividing result is divided into a first sentence and a content sentence; identifying a core word in the content sentence; determining the importance of the content sentence based on the core words in the content sentence; if the importance degree is larger than a preset threshold value, the content statement is reserved; and combining the first sentence with the reserved content sentence to construct a knowledge text.
Optionally, the content sentence is all sentences except the first sentence in the history text.
Optionally, the real-time monitoring data includes static data, dynamic data and other data; the static data comprises basic data; the dynamic data comprises protection data, scheduling data and overhaul data; the other data includes weather data and location data.
Optionally, the extracting, according to the knowledge graph, abnormal data in the real-time monitoring data includes: rejecting non-text data in the real-time monitoring data to obtain a monitoring text; and extracting abnormal data in the monitoring text through the knowledge graph.
Optionally, the fault type includes: overcurrent trip, voltage anomaly, weather fault, and mechanical fault.
Optionally, the rendering the fault analysis result includes: grading the fault analysis result to obtain a fault grade; and sending the fault grade and the fault analysis result to the target equipment.
In another aspect of the embodiments of the present invention, there is provided a fault visualization analysis system, including: the knowledge graph building module is used for acquiring historical data; preprocessing the historical data to obtain a knowledge text; extracting entity, attribute and relation triples in the knowledge text; constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result; the real-time data acquisition module is used for acquiring real-time monitoring data and a real-time running state of the target equipment; the abnormal data extraction module is used for extracting abnormal data in the real-time monitoring data according to the knowledge graph; a credibility score calculating module, configured to calculate a credibility score between the abnormal data and each fault type, where the formula is as follows:
wherein Q m Representing a confidence score between the anomaly data and a fault type m, H representing the anomaly data, H = { t = { (m) } 1 ,t 2 ,…,t i ,…,t n }，t i Indicating the ith data in the abnormal data; w is a ti Denotes t i Weight of (a), f ti,m Represents t i Number of occurrences in fault type m, N m Representing the total occurrence frequency of the fault type m in the previous year, and N representing the total fault frequency in the previous year; the target fault type determining module is used for determining a target fault type corresponding to the abnormal data based on the credibility score; the fault analysis result determining module is used for determining a fault analysis result according to the mapping relation between the real-time running state and the target fault type; and the visual display module is used for rendering the fault analysis result and carrying out visual display.
Optionally, the knowledge-graph building module is further configured to: rejecting non-text data in the historical data to obtain a historical text; sentence dividing processing is carried out on the historical text, and a sentence dividing result is divided into a first sentence and a content sentence; identifying a core word in the content sentence; determining the importance of the content sentence based on the core words in the content sentence; if the importance degree is larger than a preset threshold value, the content statement is reserved; and combining the first sentence with the reserved content sentence to construct a knowledge text.
Optionally, the content sentence is all sentences except the first sentence in the history text.
Optionally, the real-time monitoring data includes static data, dynamic data and other data; the static data comprises basic data; the dynamic data comprises protection data, scheduling data and overhaul data; the other data includes weather data and location data.
Optionally, the abnormal data extraction module is further configured to: rejecting non-text data in the real-time monitoring data to obtain a monitoring text; and extracting abnormal data in the monitoring text through the knowledge graph.
Optionally, the fault type includes: overcurrent tripping, voltage anomalies, weather faults, and mechanical faults.
Optionally, the visual display module is further configured to: grading the fault analysis result to obtain a fault grade; and sending the fault grade and the fault analysis result to the target equipment.
Has the beneficial effects that:
(1) The invention collects historical data; dividing a first sentence and a content sentence through sentence division processing; determining the importance of the content sentences based on core words in the content sentences, and reserving the content sentences with higher importance; then combining the first sentence with the reserved content sentence to construct a knowledge text; extracting entity, attribute and relation triples in the knowledge text; constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result; by the method, the microgrid operation knowledge graph is constructed, and the recognition rate of abnormal data is improved.
(2) And introducing a credibility score, and determining a target fault type corresponding to the abnormal data by calculating the credibility score between the abnormal data and each fault type. Thereby determining a more matching fault type.
(2) Determining a fault analysis result based on the knowledge graph and the target fault type; rendering the fault analysis result and carrying out visual display. Therefore, the accuracy of fault analysis is improved, and operation and maintenance personnel can obtain the operation condition of the equipment in real time.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flowchart of a fault visualization analysis method provided in an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram of a knowledge graph construction method provided by an embodiment of the application;
fig. 3 is a schematic structural diagram of a fault visualization analysis system according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without making any creative effort belong to the protection scope of the present application.
The embodiment of the application provides a fault visual analysis method and a fault visual analysis system, which comprise the steps of collecting historical data; preprocessing the historical data to obtain a knowledge text; extracting entity, attribute and relation triples in the knowledge text; constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result; acquiring real-time monitoring data and a real-time running state of target equipment; extracting abnormal data in the real-time monitoring data according to the knowledge graph; calculating a confidence score between the anomaly data and each fault type; determining a target fault type corresponding to the abnormal data based on the credibility score; determining a fault analysis result according to a mapping relation between the real-time operation state and the target fault type; and rendering the fault analysis result and performing visual display. Therefore, the accuracy of fault analysis is improved, and operation and maintenance personnel can obtain the operation condition of the equipment in real time.
The fault visualization analysis method and system can be specifically integrated in electronic equipment, and the electronic equipment can be equipment such as a terminal and a server. The terminal can be a light field camera, a vehicle-mounted camera, a mobile phone, a tablet Computer, an intelligent Bluetooth device, a notebook Computer, or a Personal Computer (PC) or other devices; the server may be a single server or a server cluster composed of a plurality of servers.
It can be understood that the fault visualization analysis method and system of the embodiment may be executed on a terminal, may also be executed on a server, and may also be executed by both the terminal and the server. The above examples should not be construed as limiting the present application.
Artificial Intelligence (AI) is a theory, method, technique and application device that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human Intelligence, perceive the environment, acquire knowledge and use the knowledge to obtain the best results. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
In recent years, with research and progress of artificial intelligence technology, artificial intelligence technology is widely applied in a plurality of fields, and the scheme provided by the embodiment of the disclosure relates to technologies such as computer vision technology and machine learning/deep learning of artificial intelligence, and is specifically described by the following embodiments:
fig. 1 shows a schematic flow chart of a fault visualization analysis method provided in an embodiment of the present application, please refer to fig. 1, which specifically includes the following steps:
and S110, acquiring real-time monitoring data and real-time running state of the target equipment.
The real-time monitoring data can comprise static data, dynamic data and other data; the static data comprises basic data; the dynamic data comprises protection data, scheduling data and overhaul data; the other data includes weather data and location data. The real-time operating state may include out-of-service, in-service, etc.
And S120, extracting abnormal data in the real-time monitoring data according to the knowledge graph.
Specifically, non-text data in the real-time monitoring data are removed to obtain a monitoring text; and extracting abnormal data in the monitoring text through the knowledge graph.
S130, calculating the credibility scores between the abnormal data and each fault type, wherein the formula is as follows:
wherein Q is m Representing a confidence score between the anomaly data and a fault type m, H representing the anomaly data, H = { t = { t } 1 ,t 2 ,…,t i ,…,t n }，t i Indicating the ith data in the abnormal data;
represents t i The weight of (a) is determined,
represents t i Number of occurrences in fault type m, N m Indicates the total number of occurrences of the fault type m in the previous year, and N indicates the total number of faults in the previous year.
In the embodiment, the fault data of the previous year is taken as a reference, all the current abnormal data participate in calculation, and the more matched fault type can be accurately determined.
The fault types can be overcurrent tripping, voltage abnormity, weather fault and mechanical fault.
S140, determining a target fault type corresponding to the abnormal data based on the credibility score.
Wherein the target failure type may be one or more.
Specifically, a first threshold value is preset, and fault types corresponding to the reliability scores greater than the first threshold value are all used as target fault types corresponding to the abnormal data.
It should be noted that the first threshold may take a value according to the historical failure frequency and the failure severity of the target device, and is not specifically limited herein.
S150, determining a fault analysis result according to the mapping relation between the real-time running state and the target fault type.
For example, the real-time running state is "in work", the target fault type is "mechanical fault", and according to the mapping relationship between the two, the fault analysis result is determined to be "target equipment is immediately closed, and emergency repair work is performed".
And S160, rendering the fault analysis result and carrying out visual display.
Wherein, the failure analysis result can be visually displayed through the mobile terminal or the PC terminal.
Specifically, the fault analysis results are classified to obtain fault grades; and sending the fault grade and the fault analysis result to the target equipment.
For example, the failure levels are divided into a primary failure, a secondary failure and a tertiary failure according to the severity, wherein the primary failure is rendered as red, the secondary failure is rendered as yellow, and the tertiary failure is rendered as blue.
For another example, the failure levels are divided into an urgent failure and a transient failure according to the processing order from high to low, and text is rendered in red for the urgent failure and in blue for the transient failure.
Further, the following steps are also included after step S160:
and sending an alarm signal according to the fault analysis result, and receiving the alarm signal and executing corresponding processing by operation and maintenance personnel.
By the method, the abnormal data are extracted, the credibility score between the abnormal data and the fault type is calculated, the accuracy of fault analysis can be improved, and meanwhile, the fault analysis result is visually displayed, so that operation and maintenance personnel can acquire the running condition of the equipment in real time.
Fig. 2 shows a schematic flow chart of a method for constructing a knowledge graph provided in an embodiment of the present application, please refer to fig. 2, which specifically includes the following steps:
and S210, collecting historical data.
The historical data includes static data, dynamic data and other data. The static data can be device basic data and device access data. The dynamic data may be protection data, scheduling data, overhaul data, and telemetry data. Other data may be weather data, location data, and scheduling data.
S220, eliminating non-text data in the historical data to obtain a historical text.
And S230, performing sentence splitting processing on the historical text, and dividing a sentence splitting result into a first sentence and a content sentence.
Wherein, the content sentences are all sentences except the first sentence in the history text.
S240, identifying core words in the content sentences.
Optionally, performing word segmentation on the content sentence, labeling each word segmentation by using a part-of-speech tagging mode, and keeping a verb and a noun as core words.
Optionally, the content sentence is subjected to word segmentation, a named entity recognition technology is adopted to recognize the content entity in the sentence, and the entity is reserved as a core word.
For example, the history is "2022, 3/5/d, and the device 1 of a certain electric power company, located in shandong province, is continuously operated to perform the reclosing action". After this sentence division processing, a first sentence "3/5/2022" and a content sentence "a certain electric power company is located in the facility 1 of Shandong province, and the facility continues to operate and execute a reclosing operation" are divided. Verbs and nouns in the content sentence are reserved as core words, namely { "a certain power company", "shandong province", "equipment 1", "operation", "execution", "reclosing action" }.
S250, determining the importance of the content sentence based on the core words in the content sentence.
Specifically, an electric power field dictionary is preset, the field dictionary comprises field words and corresponding weight values, the core words are matched with the field dictionary, and the successfully matched core words and the corresponding weight values are obtained.
Further, core words in the same content sentence are obtained, and the importance of the content sentence is calculated through the following formula:
wherein, { w 1 ,w 2 ,…,w n Denotes core words in the same content sentence, n denotes a total of n core words in the content sentence, { c 1 ,c 2 ,…,c n And represents the corresponding weight of the core word.
And S260, if the importance is greater than a preset threshold, reserving the content statement.
Specifically, a second threshold is preset, and if the importance of a certain content statement is greater than the second threshold, the content statement is retained.
It should be noted that the second threshold may be a value according to the scale of the historical data, for example, if the scale of the historical data is very large, a higher second threshold is set, and the second threshold is not specifically limited herein.
And S270, combining the first sentence with the reserved content sentence to construct a knowledge text.
In the above example, the content sentence retained is "a certain power company is located in the equipment 1 of Shandong province, and performs reclosing action"; furthermore, the first sentence and the reserved content sentence are combined to construct a knowledge text of "3, 5 and 2022, a certain electric power company is located in equipment 1 of Shandong province to execute reclosing action".
Through the process, the knowledge text highly related to the fault is extracted, and the constructed knowledge graph has better quality.
And S280, extracting entity, attribute and relationship triples in the knowledge text.
Specifically, a triple (entity-attribute-relationship) is constructed using semantic dependency analysis.
Wherein, named entity recognition technology can be adopted to recognize the entities in the knowledge text.
And S290, constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result.
The knowledge graph is a knowledge graph in the field of electric power.
Optionally, the association rule mining algorithm specifically includes two steps of frequent item set mining and association rule generation.
Optionally, an association model may be further constructed, and the knowledge graph is constructed by using the association model.
By the method, the microgrid operation knowledge graph is constructed, and the recognition rate of abnormal data in the fault visualization analysis process can be improved.
To implement the above method class embodiments, this embodiment further provides a fault visualization analysis system, as shown in fig. 3, where the system includes:
a knowledge graph construction module 310 for collecting historical data; preprocessing the historical data to obtain a knowledge text; extracting entity, attribute and relation triples in the knowledge text; and constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result.
And the real-time data acquisition module 320 is configured to acquire real-time monitoring data and a real-time operation state of the target device.
And the abnormal data extraction module 330 is configured to extract abnormal data in the real-time monitoring data according to the knowledge graph.
A confidence score calculating module 340, configured to calculate a confidence score between the abnormal data and each fault type, where the formula is as follows:
wherein Q is m Representing a confidence score between the anomaly data and a fault type m, H representing the anomaly data, H = { t = { t } 1 ,t 2 ,…,t i ,…,t n }，t i Indicating the ith data in the abnormal data;
denotes t i The weight of (a) is calculated,
represents t i Number of occurrences in fault type m, N m The total occurrence frequency of the fault type m in the previous year is represented, and the total fault frequency in the previous year is represented by N; and the target fault type determining module is used for determining a target fault type corresponding to the abnormal data based on the credibility score.
And a fault analysis result determining module 350, configured to determine a fault analysis result according to a mapping relationship between the real-time operating state and the target fault type.
And the visual display module 360 is used for rendering the fault analysis result and carrying out visual display.
Optionally, the knowledge-graph building module 310 is further configured to: rejecting non-text data in the historical data to obtain a historical text; sentence dividing processing is carried out on the historical text, and a sentence dividing result is divided into a first sentence and a content sentence; identifying a core word in the content sentence; determining the importance of the content sentence based on the core words in the content sentence; if the importance degree is larger than a preset threshold value, the content statement is reserved; and combining the first sentence with the reserved content sentence to construct a knowledge text.
Optionally, the content sentence is all sentences except the first sentence in the history text.
Optionally, the real-time monitoring data includes static data, dynamic data and other data; the static data comprises basic data; the dynamic data comprises protection data, scheduling data and overhaul data; the other data includes weather data and location data.
Optionally, the abnormal data extracting module 330 is further configured to: rejecting non-text data in the real-time monitoring data to obtain a monitoring text; and extracting abnormal data in the monitoring text through the knowledge graph.
Optionally, the fault type includes: overcurrent trip, voltage anomaly, weather fault, and mechanical fault.
Optionally, the visual display module 360 is further configured to: grading the fault analysis result to obtain a fault grade; and sending the fault grade and the fault analysis result to the target equipment.
Furthermore, the system can also comprise an alarm module which is used for sending an alarm signal according to the fault analysis result, and the operation and maintenance personnel receive the alarm signal and execute corresponding processing.
The fault visualization analysis system introduces credibility scores, and determines target fault types and fault analysis results corresponding to abnormal data by calculating the credibility scores between the abnormal data and each fault type; and rendering the fault analysis result and performing visual display. Therefore, the accuracy of fault analysis is improved, and operation and maintenance personnel can obtain the running condition of the equipment in real time.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the modules/units/sub-units/components in the above-described apparatus may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the units into only one type of logical function may be implemented in other ways, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk, and various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures, and moreover, the terms "first," "second," "third," etc. are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present application, and are used for illustrating the technical solutions of the present application, but not limiting the same, and the scope of the present application is not limited thereto, and although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: those skilled in the art can still make modifications or changes to the embodiments described in the foregoing embodiments, or make equivalent substitutions for some features, within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present application. Are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. A fault visualization analysis method is characterized by comprising the following steps:
collecting historical data;
preprocessing the historical data to obtain a knowledge text;
extracting entity, attribute and relation triples in the knowledge text;
constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result;
acquiring real-time monitoring data and a real-time running state of target equipment;
extracting abnormal data in the real-time monitoring data according to the knowledge graph;
calculating the credibility scores between the abnormal data and each fault type, wherein the formula is as follows:
wherein Q is m Representing a confidence score between the anomaly data and a fault type m, H representing the anomaly data, H = { t = { t } 1 ,t 2 ,…,t i ,…,t n }，t i Representing the ith data in the abnormal data;
denotes t i The weight of (a) is determined,
denotes t i Number of occurrences in fault type m, N m Representing the total occurrence frequency of the fault type m in the previous year, and N representing the total fault frequency in the previous year;
determining a target fault type corresponding to the abnormal data based on the credibility score;
determining a fault analysis result according to a mapping relation between the real-time running state and the target fault type;
and rendering the fault analysis result and performing visual display.
2. The method of claim 1, wherein preprocessing the historical data to obtain a knowledge text comprises:
rejecting non-text data in the historical data to obtain a historical text;
sentence division processing is carried out on the historical text, and a sentence division result is divided into a first sentence and a content sentence;
identifying a core word in the content sentence;
determining the importance of the content sentence based on the core words in the content sentence;
if the importance degree is larger than a preset threshold value, the content statement is reserved;
and combining the first sentence with the reserved content sentence to construct a knowledge text.
3. The method of claim 2, wherein the content sentence is all but a first sentence in the historical text.
4. The method of claim 1, wherein the real-time monitoring data comprises static data, dynamic data, and other data;
the static data comprises basic data;
the dynamic data comprises protection data, scheduling data and overhaul data;
the other data includes weather data and location data.
5. The method of claim 1, wherein extracting abnormal data from the real-time monitoring data according to the knowledge-graph comprises:
rejecting non-text data in the real-time monitoring data to obtain a monitoring text;
and extracting abnormal data in the monitoring text through the knowledge graph.
6. The method of claim 1, wherein the fault type comprises: overcurrent tripping, voltage anomalies, weather faults, and mechanical faults.
7. The method of claim 1, wherein the rendering the fault analysis results comprises:
grading the fault analysis result to obtain a fault grade;
and sending the fault grade and the fault analysis result to the target equipment.
8. A fault visualization analysis system, comprising:
the knowledge graph building module is used for acquiring historical data; preprocessing the historical data to obtain a knowledge text; extracting entity, attribute and relation triples in the knowledge text; constructing a knowledge graph by adopting an association rule mining algorithm according to the extraction result; the real-time data acquisition module is used for acquiring real-time monitoring data and a real-time running state of the target equipment; the abnormal data extraction module is used for extracting abnormal data in the real-time monitoring data according to the knowledge graph;
a confidence score calculating module, configured to calculate a confidence score between the abnormal data and each fault type, where the formula is as follows:
wherein Q is m Representing a confidence score between the anomaly data and a fault type m, H representing the anomaly data, H = { t = { t } 1 ,t 2 ,…,t i ,…,t n }，t i Indicating the ith data in the abnormal data;
represents t i The weight of (a) is determined,
denotes t i Number of occurrences in fault type m, N m Representing the total occurrence frequency of the fault type m in the previous year, and N representing the total fault frequency in the previous year;
the target fault type determining module is used for determining a target fault type corresponding to the abnormal data based on the credibility score;
the fault analysis result determining module is used for determining a fault analysis result according to the mapping relation between the real-time running state and the target fault type;
and the visual display module is used for rendering the fault analysis result and carrying out visual display.
9. The system of claim 8, wherein the knowledge-graph building module is further configured to:
rejecting non-text data in the historical data to obtain a historical text;
sentence division processing is carried out on the historical text, and a sentence division result is divided into a first sentence and a content sentence;
identifying a core word in the content sentence;
determining the importance of the content sentence based on the core words in the content sentence;
if the importance degree is larger than a preset threshold value, the content statement is reserved;
and combining the first sentence with the reserved content sentence to construct a knowledge text.
10. The method of claim 9, wherein the content sentence is all but a first sentence in the historical text.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210748871.6A CN115186054A (en) | 2022-06-29 | 2022-06-29 | Fault visualization analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210748871.6A CN115186054A (en) | 2022-06-29 | 2022-06-29 | Fault visualization analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115186054A true CN115186054A (en) | 2022-10-14 |
Family
ID=83514969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210748871.6A Pending CN115186054A (en) | 2022-06-29 | 2022-06-29 | Fault visualization analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115186054A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118011990A (en) * | 2024-04-10 | 2024-05-10 | 中国标准化研究院 | Industrial data quality monitoring and improving system based on artificial intelligence |
-
2022
- 2022-06-29 CN CN202210748871.6A patent/CN115186054A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118011990A (en) * | 2024-04-10 | 2024-05-10 | 中国标准化研究院 | Industrial data quality monitoring and improving system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544399B (en) | Power transmission equipment state evaluation method and device based on multi-source heterogeneous data | |
| CN108304567B (en) | Method and system for identifying working condition mode and classifying data of high-voltage transformer | |
| CN116089231B (en) | Fault alarm method and device, electronic equipment and storage medium | |
| CN114723285A (en) | Power grid equipment safety evaluation prediction method | |
| CN112036185B (en) | Method and device for constructing named entity recognition model based on industrial enterprise | |
| CN115186054A (en) | Fault visualization analysis method and system | |
| CN112906764A (en) | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network | |
| CN116028646A (en) | Power grid dispatching field knowledge graph construction method based on machine learning | |
| CN115438663A (en) | Risk analysis method, device, equipment and medium for power grid work bill | |
| CN117592870A (en) | Comprehensive analysis system based on water environment monitoring information | |
| CN116956896A (en) | Text analysis method, system, electronic equipment and medium based on artificial intelligence | |
| CN115619117A (en) | Power grid intelligent scheduling method based on duty system | |
| CN115168562A (en) | Method, device, equipment and medium for constructing intelligent question-answering system | |
| An et al. | Real-time Statistical Log Anomaly Detection with Continuous AIOps Learning. | |
| CN117874200A (en) | Answer text generation method, device, equipment and medium for wind power operation and maintenance data | |
| CN115641549B (en) | Health monitoring method and system for main propulsion diesel unit | |
| CN117350700A (en) | Event auxiliary decision-making method and system based on latent semantic analysis | |
| CN117313845A (en) | Power grid fault detection auxiliary method and system based on knowledge graph | |
| CN112784080B (en) | Scene recommendation method, system and device based on three-dimensional digital platform of power plant | |
| CN113807462A (en) | AI-based network equipment fault reason positioning method and system | |
| Zhang et al. | Grid monitoring alarm event recognition method integrating expert rules and deep learning | |
| CN118552180A (en) | Power equipment management method and system based on Internet of things | |
| Chu et al. | Information Semantic Mining Method for Risk Warning Scenarios of Electric Power Field Operations | |
| Chen et al. | Sensitive Information Identification Method of Power System Based on Deep Learning | |
| CN118312623A (en) | Construction method, device, equipment and storage medium of fault identification knowledge graph |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |